location:Home > 2019 VOL.2 Aug No.4 > Research on Parallel Prediction Model of Short-term Power Load Big Data

2019 VOL.2 Aug No.4

  • Title: Research on Parallel Prediction Model of Short-term Power Load Big Data
  • Name: Quincy Robin
  • Company: Nanyang Technological University
  • Abstract:

    The parallel prediction model of traditional power load big data has the problem of low prediction accuracy under different working conditions. For this reason, the parallel prediction model of short-term power load big data is designed. The short-term electric load forecasting theory is analyzed, and the short-term electric load big data is classified to select the short-term electric load big data prediction theory. Based on the theory, the Map/Reduce framework is built, and the forecasting process is designed through the Map/Reduce framework to predict the short-term power load big data of the subnet and the short-term power load big data of the whole network. Construction of a parallel prediction model for realizing short-term power load big data. The experimental results show that the designed big data parallel prediction model improves the prediction accuracy by 11%-12% compared with the traditional model, and can switch between different working states.

  • Keyword: Short-Term Load Forecasting; Big Data; Power Load; Prediction Algorithm;
  • DOI: 10.12250/jpciams2019040132
  • Citation form: Quincy Robin.Research on Parallel Prediction Model of Short-term Power Load Big Data[J]. Computer Informatization and Mechanical System, 2019, vol. 2, pp. 1-5.
Reference:

[1] Zhou Mo, Jin Min. Short-term electric load forecasting method combined with multi-algorithm multi-model and online second learning[J]. Journal of Computer Applications, 2017, 37(11):3317-3322.

[2] Xiong Junhua, Niu Ke, Zhang Chunge, et al. Research on short-term load forecasting method based on wavelet mutation fruit fly optimization support vector machine[J]. Power System Protection and Control, 2017, 45(13):71-77.

[3] LIU Dandan, ZHU Jiaming, HUANG Tingting. Short-term electric load forecasting based on time series and grey model[J]. Journal of Qiqihar University(Natural Science Edition), 2017, 33(3):7-12. 

[4] LI Li, YANG Shengfeng, QIU Jinpeng, et al. Simulation study of short-term load forecasting method for power system power supply[J]. Computer Simulation, 2017, 34(1):104-108.

[5] Wang Weiguo, Dou Zhenhai, Shen Jin, et al. Short-term load forecasting based on inverse fuzzy theory to improve fuzzy mean-generation function[J]. Hydropower Science, 2017, 14(12):208-211. 

[6] Liang Zhi, Sun Guoqiang, Wei Zhinong, et al. Short-term load forecasting based on variable selection and Gaussian process regression[J]. Electric Power Construction, 2017, 38(2):122-128. 

[7] Song Renjie, Yu Tong, Chen Yuhong, et al. Big data similar repeated record detection algorithm based on MapReduce model[J]. Journal of Shanghai Jiaotong University, 2018, 52(2):214-221.

[8] Xiao Wen, Hu Juan, Zhou Xiaofeng. A review of parallel association rule mining algorithms based on MapReduce computational model[J]. Journal of Computer Applications, 2018, 38(1):132-139.

[9] Lei Jingsheng, Hao Wei, Zhu Guokang. Short-term electric load forecasting based on “stratification-collection” model[J]. Electric Power Construction, 2017, 38(1):68-75. 

[10] Su Xueneng, Liu Tianqi, Cao Hongqian, et al. Short-term load forecasting method based on Hadoop architecture for multiple distributed BP neural networks[J]. Chinese Society for Electrical Engineering, 2017, 37(17):4966-4973.


 


Tsuruta Institute of Medical Information Technology
Address:[502,5-47-6], Tsuyama, Tsukuba, Saitama, Japan TEL:008148-28809 fax:008148-28808 Japan,Email:jpciams@hotmail.com,2019-09-16